Research map / Label-efficient and robust learning / Recognition and long-tail
Neural Feature Search for RGB-Infrared Person Re-Identification
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use dual-level neural feature search (ablation) | two-stream ResNet-50 ReID · SYSU-MM01 single-shot, all search | Rank-1: 47.00 -> 48.91 | Helped |
| use dual-level neural feature search (ablation) | two-stream ResNet-50 ReID · SYSU-MM01 single-shot, all search | mAP: 46.46 -> 47.92 | Helped |
| add cross-modality contrastive optimization (ablation) | two-stream ResNet-50 ReID · SYSU-MM01 single-shot, all search | Rank-1: 47.00 -> 52.29 | Helped |
| add cross-modality contrastive optimization (ablation) | two-stream ResNet-50 ReID · SYSU-MM01 single-shot, all search | mAP: 46.46 -> 50.91 | Helped |
| add contrastive optimization to neural feature search (ablation) | Baseline + NFS block · SYSU-MM01 single-shot, all search | Rank-1: 48.91 -> 56.91 | Helped |
| add contrastive optimization to neural feature search (ablation) | Baseline + NFS block · SYSU-MM01 single-shot, all search | mAP: 47.92 -> 55.45 | Helped |
| search at Stages 1, 2, and 3 instead of Stages 1, 2, and 3, 4 (ablation) | NFS · SYSU-MM01 single-shot, all search | Rank-1: 55.18 -> 56.91 | Helped |
| search at Stages 1, 2, and 3 instead of Stages 1, 2, and 3, 4 (ablation) | NFS · SYSU-MM01 single-shot, all search | mAP: 54.21 -> 55.45 | Helped |
| replace DDAG with NFS | RGB-IR ReID · RegDB visible-to-infrared | Rank-1: 69.34 -> 80.54 | Helped |
| replace DDAG with NFS | RGB-IR ReID · RegDB visible-to-infrared | mAP: 63.46 -> 72.10 | Helped |
Closest papers by meaning
- Empowering Visible-Infrared Person Re-Identification with Large Foundation Models (NeurIPS 2024 · similarity 0.90)
- Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.89)
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.89)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.89)
- High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-identification (AAAI 2024 · similarity 0.88)
- Cross-Modality Perturbation Synergy Attack for Person Re-identification (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.